no code implementations • 12 Mar 2024 • Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier
We propose a novel Transformer-based module to address the data association problem for multi-object tracking.
1 code implementation • 5 Mar 2024 • Katia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau
In the learning phase, we consider the radius as proportional to a standard deviation in order to compute the error to propagate on a set of two-dimensional Gaussian functions rather than disks.
1 code implementation • 28 Feb 2024 • Khalil Sabri, Célia Djilali, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Wassim Bouachir
Urban traffic environments present unique challenges for object detection, particularly with the increasing presence of micromobility vehicles like e-scooters and bikes.
no code implementations • 16 Feb 2024 • Noreen Anwar, Guillaume-Alexandre Bilodeau, Wassim Bouachir
The objective of our work is to leverage this complementary information to improve detection.
1 code implementation • 11 Dec 2023 • Xi Ye, Guillaume-Alexandre Bilodeau
Predicting future frames of a video is challenging because it is difficult to learn the uncertainty of the underlying factors influencing their contents.
1 code implementation • 6 Nov 2023 • Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau
Our experimental results show that our approach is effective for detecting the different stages of Parkinson's disease from gait data, with a final accuracy of 88%, outperforming other state-of-the-art AI methods on the Physionet gait dataset.
1 code implementation • 26 Oct 2023 • Safwen Naimi, Wassim Bouachir, Guillaume-Alexandre Bilodeau
Our hybrid architecture exploits the strengths of both Convolutional Neural Networks (ConvNets) and Transformers to accurately detect PD and determine the severity stage.
no code implementations • 26 Oct 2023 • Safwen Naimi, Olfa Koubaa, Wassim Bouachir, Guillaume-Alexandre Bilodeau, Gregory Jeddore, Patricia Baines, David Correia, Andre Arsenault
These cameras are used by ecologists in Newfoundland and Labrador to subsequently analyze and manually segment the images to determine lichen thalli condition and change.
1 code implementation • 9 May 2023 • Katia Jodogne-Del Litto, Guillaume-Alexandre Bilodeau
In this paper, we improve over CenterPoly by enhancing the classical regression L1 loss with a novel region-based loss and a novel order loss, as well as with a new training process for the vertices prediction head.
1 code implementation • 22 Apr 2023 • Noreen Anwar, Philippe Duplessis-Guindon, Guillaume-Alexandre Bilodeau, Wassim Bouachir
To address the aforementioned challenges, this paper proposes a novel approach where a high-resolution convolutional neural network is used to better capture relationships between the two spectra.
1 code implementation • 18 Apr 2023 • Andrey Sobolevsky, Guillaume-Alexandre Bilodeau, Jinghui Cheng, Jin L. C. Guo
Arranging all components inside a GUI layout manually is a time-consuming task.
1 code implementation • 12 Apr 2023 • Jacob Meilleur, Guillaume-Alexandre Bilodeau
We propose TopTrack, a joint detection-and-tracking method that uses the top of the object as a keypoint for detection instead of the center because it is more often visible.
1 code implementation • 12 Dec 2022 • Xi Ye, Guillaume-Alexandre Bilodeau
Video prediction is a challenging computer vision task that has a wide range of applications.
1 code implementation • 11 Oct 2022 • Xi Ye, Guillaume-Alexandre Bilodeau
Different conditional video prediction tasks, like video future frame prediction and video frame interpolation, are normally solved by task-related models even though they share many common underlying characteristics.
no code implementations • 22 Apr 2022 • Rémi Nahon, Guillaume-Alexandre Bilodeau, Gilles Pesant
In the second phase, we associate the previously constructed tracklets using a Belief Propagation Constraint Programming algorithm, where we propose various constraints that assign scores to each of the tracklets based on multiple characteristics, such as their dynamics or the distance between them in time and space.
no code implementations • 19 Apr 2022 • Philippe Duplessis-Guindon, Guillaume-Alexandre Bilodeau
A lot of work has been done in classical stereoscopy, but multispectral stereoscopy is not studied as frequently.
no code implementations • 19 Apr 2022 • Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier
Human action recognition (HAR) in videos is one of the core tasks of video understanding.
1 code implementation • 1 Apr 2022 • Duc Minh Dimitri Nguyen, Mehdi Miah, Guillaume-Alexandre Bilodeau, Wassim Bouachir
This paper focuses on the detection of Parkinson's disease based on the analysis of a patient's gait.
1 code implementation • 29 Mar 2022 • Xi Ye, Guillaume-Alexandre Bilodeau
Based on this new Transformer block, a fully autoregressive video future frames prediction Transformer is proposed.
no code implementations • 5 Nov 2021 • Maude Nguyen-The, Guillaume-Alexandre Bilodeau, Jan Rockemann
Identifying and understanding underlying sentiment or emotions in text is a key component of multiple natural language processing applications.
1 code implementation • 2 Nov 2021 • Gaspar Faure, Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier
In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons.
Multi-Object Tracking Multi-Object Tracking and Segmentation +1
no code implementations • 21 Oct 2021 • Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier
We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets.
no code implementations • 25 Sep 2021 • Oumayma Messoussi, Felipe Gohring de Magalhaes, Francois Lamarre, Francis Perreault, Ibrahima Sogoba, Guillaume-Alexandre Bilodeau, Gabriela Nicolescu
Detecting and tracking vehicles in urban scenes is a crucial step in many traffic-related applications as it helps to improve road user safety among other benefits.
1 code implementation • 15 Sep 2021 • Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Maguelonne Héritier
We propose FFAVOD, standing for feature fusion architecture for video object detection.
Ranked #2 on Object Detection on UA-DETRAC
1 code implementation • 19 Aug 2021 • Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Maguelonne Héritier
The models were trained and evaluated on Cityscapes, KITTI and IDD and the results are reported on their public benchmark, which are state-of-the-art at real-time speeds.
Ranked #1 on Real-time Instance Segmentation on Cityscapes test
no code implementations • 15 Jul 2021 • Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier
We propose a method for multi-object tracking and segmentation (MOTS) that does not require fine-tuning or per benchmark hyperparameter selection.
1 code implementation • 10 Jun 2021 • Pankaj Raj Roy, Guillaume-Alexandre Bilodeau, Lama Seoud
We present a local anomaly detection method in videos.
1 code implementation • 1 Mar 2021 • Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir
Siamese trackers demonstrated high performance in object tracking due to their balance between accuracy and speed.
1 code implementation • 1 Mar 2021 • Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir
Based on this advanced feature representation, our algorithm achieves high tracking accuracy, while outperforming several state-of-the-art trackers, including standard Siamese trackers.
no code implementations • 13 Nov 2020 • Pankaj Raj Roy, Guillaume-Alexandre Bilodeau, Lama Seoud
We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in videos.
no code implementations • 17 Oct 2020 • Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier
Human action recognition (HAR) in videos is a fundamental research topic in computer vision.
1 code implementation • 15 Oct 2020 • Mehdi Miah, Justine Pepin, Nicolas Saunier, Guillaume-Alexandre Bilodeau
Commonly used features are color histograms, histograms of oriented gradients, deep features from convolutional neural networks and re-identification (ReID) features.
no code implementations • 30 Jul 2020 • Yacine Khraimeche, Guillaume-Alexandre Bilodeau, David Steele, Harshad Mahadik
Our framework jointly trains a ReID network for discriminative features extraction in a source labelled domain using identity annotation, and adapts the ReID model to an unlabelled target domain by learning disentangled latent representations on the domain.
no code implementations • 30 Apr 2020 • David-Alexandre Beaupre, Guillaume-Alexandre Bilodeau
Multispectral disparity estimation is a difficult task for many reasons: it has all the same challenges as traditional visible-visible disparity estimation (occlusions, repetitive patterns, textureless surfaces), in addition of having very few common visual information between images (e. g. color information vs. thermal information).
1 code implementation • 30 Mar 2020 • Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier
In this paper, we propose a multiple object tracker, called MF-Tracker, that integrates multiple classical features (spatial distances and colours) and modern features (detection labels and re-identification features) in its tracking framework.
1 code implementation • 24 Mar 2020 • Hughes Perreault, Maguelonne Héritier, Pierre Gravel, Guillaume-Alexandre Bilodeau, Nicolas Saunier
Consecutive frames in a video are highly redundant.
Ranked #4 on Object Detection on UAVDT
no code implementations • 10 Mar 2020 • Alexandre Pineault, Guillaume-Alexandre Bilodeau, Gilles Pesant
Because our focus is on the data association problem, our MOT method only uses simple image features, which are the center position and color of detections for each frame.
1 code implementation • 13 Feb 2020 • Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Maguelonne Héritier
We use those segmentation maps inside the network as a self-attention mechanism to weight the feature map used to produce the bounding boxes, decreasing the signal of non-relevant areas.
Ranked #3 on Object Detection on UA-DETRAC
1 code implementation • 29 Nov 2019 • Jules Simon, Guillaume-Alexandre Bilodeau, David Steele, Harshad Mahadik
We propose a method based on binary search trees and a large peer-labelled color name dataset.
1 code implementation • Expert Systems with Applications 2020 • Imanne El Maachi, Guillaume-Alexandre Bilodeau, Wassim Bouachir
To our knowledge, this is the state-of-the-start performance in Parkinson's gait recognition.
no code implementations • 15 May 2019 • Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier
In this paper, we propose to combine detections from background subtraction and from a multiclass object detector for multiple object tracking (MOT) in urban traffic scenes.
1 code implementation • 28 Mar 2019 • Hughes Perreault, Guillaume-Alexandre Bilodeau, Nicolas Saunier, Pierre Gravel
Two new models, RetinaNet-Double and RetinaNet-Flow, are proposed, based respectively on the concatenation of a target frame with a preceding frame, and the concatenation of the optical flow with the target frame.
1 code implementation • 26 Mar 2019 • Pankaj Raj Roy, Guillaume-Alexandre Bilodeau
We address the problem of abnormal event detection from trajectory data.
1 code implementation • 8 Sep 2018 • Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau, Robert Bergevin
The segmentation of video sequences into foreground and background regions is a low-level process commonly used in video content analysis and smart surveillance applications.
no code implementations • 6 Sep 2018 • Hui-Lee Ooi, Guillaume-Alexandre Bilodeau, Nicolas Saunier, David-Alexandre Beaupré
Multiple object tracking (MOT) in urban traffic aims to produce the trajectories of the different road users that move across the field of view with different directions and speeds and that can have varying appearances and sizes.
1 code implementation • 25 Aug 2018 • Pankaj Raj Roy, Guillaume-Alexandre Bilodeau
In this paper, we focus on the development of a method that detects abnormal trajectories of road users at traffic intersections.
no code implementations • 22 Aug 2018 • Zhenxi Li, Guillaume-Alexandre Bilodeau, Wassim Bouachir
In this paper, we propose a robust object tracking algorithm based on a branch selection mechanism to choose the most efficient object representations from multi-branch siamese networks.
no code implementations • 29 Jan 2018 • David-Alexandre Beaupré, Guillaume-Alexandre Bilodeau, Nicolas Saunier
In this paper, we present a new method for detecting road users in an urban environment which leads to an improvement in multiple object tracking.
no code implementations • 10 Jan 2018 • Farnoosh Ghadiri, Robert Bergevin, Guillaume-Alexandre Bilodeau
We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales.
1 code implementation • 6 Jan 2018 • Fania Mokhayeri, Eric Granger, Guillaume-Alexandre Bilodeau
A compact set of synthetic faces is generated that resemble individuals of interest under the capture conditions relevant to the OD.
no code implementations • 12 Nov 2017 • Yucao Tang, Guillaume-Alexandre Bilodeau
Compared to tracking with a still camera, the images captured with a PTZ camera are highly dynamic in nature because the camera can perform large motion resulting in quickly changing capture conditions.
1 code implementation • 29 Jun 2017 • Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger
This paper addresses the problem of appearance matching across different challenges while doing visual face tracking in real-world scenarios.
no code implementations • 1 Jun 2017 • Melvin Wong, Bilal Farooq, Guillaume-Alexandre Bilodeau
Our findings show that through non-parametric statistical tests, we can extract useful latent information on the behaviour of latent constructs through machine learning methods and present strong and significant influence on the choice process.
2 code implementations • 7 Feb 2017 • Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger
In this paper, an online adaptive model-free tracker is proposed to track single objects in video sequences to deal with real-world tracking challenges like low-resolution, object deformation, occlusion and motion blur.
1 code implementation • 8 Nov 2016 • Yuebin Yang, Guillaume-Alexandre Bilodeau
In this paper, we investigate how a robust visual tracker like KCF can improve multiple object tracking.
no code implementations • 23 Oct 2016 • François-Xavier Derue, Guillaume-Alexandre Bilodeau, Robert Bergevin
In visual tracking, part-based trackers are attractive since they are robust against occlusion and deformation.
no code implementations • 18 May 2015 • Gengjie Chen, Pierre-Luc St-Charles, Wassim Bouachir, Thomas Joeisseint, Guillaume-Alexandre Bilodeau, Robert Bergevin
Tracking with a Pan-Tilt-Zoom (PTZ) camera has been a research topic in computer vision for many years.
no code implementations • 17 Mar 2014 • Tanushri Chakravorty, Guillaume-Alexandre Bilodeau, Eric Granger
To achieve a global affine transformation that maximises the overlapping of infrared and visible foreground pixels, the matched keypoints of each local shape polygon are stored temporally in a buffer for a few number of frames.
no code implementations • 14 May 2013 • Wassim Bouachir, Atousa Torabi, Guillaume-Alexandre Bilodeau, Pascal Blais
This paper proposes a semantic segmentation method for outdoor scenes captured by a surveillance camera.